Network management tasks are increasing its complexity because of the development of the IoT environment, virtualization technologies. To keep the safety and security of the network systems, the advances of analysis method for various network data is required for the practical problem-solving. Although many IT tools to support the data analysis works in network management, it is not enough for adaptation to developing environment. Also, the solutions do not consider the knowledge variety of users. In this paper, we propose an agent-based approach for data presentation to support the analysis from multiple aspects in network management works. Concretely, we design the self-organized analysis procedure based on the cooperation among agents and the interactive requirement estimation mechanism to improve the support functions for the diverse of the users’ knowledge. The evaluation experiments show the effectiveness of the prototypical system designed according to the proposed approach.